Evidence-Base Automation for Document Dissemination

Recent innovations in information collection have vastly increased the amount of digital content available. Providing collaborators with access to this information during day to day activities is vital. However, search services that tie together information across multiple security domains cannot be deployed because of the potential for unsafe information dissemination.  Search results and the requested documents must be cleared for the requesting user before they can be presented; however, involving human reviewers in this information retrieval process is not a sustainable solution. Thus, automated tools need to be incorporated with search services and with the human review process to improve security without adding costs for the users or unduly burdening the information providers. We present an evidence-based approach to information management and dissemination that leverages the state-of-the-art in natural language processing and automated classification technologies. Our approach takes a gradual path to increasing automation by developing techniques based on active learning that can be incorporated into existing workflows. As the proposed system learns from the user''''''''''''''''s activities, it will increasingly provide support to the user''''''''''''''''s tasks. This approach will build trust, allowing the system to gradually provide increasingly automated secure information dissemination. BENEFIT: Many areas of the commercial sector have a pressing need for tools designed to improve information dissemination efficiency and security. The recent development of the Health Insurance Portability and Accountability Act (HIPAA) of 1996 and Sarbanes-Oxley Act of 2002 have made these requirements more pressing than ever. Our proposed approach incorporates state-of-the-art text analysis and information management technologies with existing search tools to manage information retrieval, both of individual documents and aggregates, in an efficient and secure manner.